Abstract
The now classical collocation method in geodesy has been derived byH. Moritz (1970; 1973) within an appropriate Mixed Linear Model. According toB. Schaffrin (1985; 1986) even a generalized form of the collocation solution can be proved to represent a combined estimation/prediction procedure of typeBLUUE (Best Linear Uniformly Unbiased Estimation) for the fixed parameters, and of type inhomBLIP (Best inhomogeneously LInear Prediction) for the random effects with not necessarily zero expectation. Moreover, “robust collocation” has been introduced by means of homBLUP (Best homogeneously Linear weakly Unbiased Prediction) for the random effects together with a suitableLUUE for the fixed parameters. Here we present anequivalence theorem which states that the robust collocation solution in theoriginal Mixed Linear Model can identically be derived as traditionalLESS (LEast Squares Solution) in amodified Mixed Linear Model without using artifacts like “pseudo-observations”. This allows us a nice interpretation of “robust collocation” as an adjustment technique in the presence of “weak prior information”.
Similar content being viewed by others
References
A. BJERHAMMAR: Theory of Errors and Generalized Matrix Inverses. Elsevier: Amsterdam, etc. 1973.
A. DERMANIS: Geodetic applications of interpolation and prediction. Eratosthenes22 (1988), pp. 229–262.
D. HARVILLE: Extension of the Gauss-Markov theorem to include the estimation of random effects. Ann. Statist.4 (1976), pp. 384–395.
K.R. KOCH: Parameter Estimation and Hypothesis Tests in Linear Models. Springer: Berlin, etc. 1988.
E.J. KRAKIWSKY: The method of least squares: A synthesis of advances. Dept. of Surveying Eng., The University of Calgary, Publ. No.10003, Calgary/Alberta 1989 (last reprint).
H. LÄUTER: Optimale Vorhersage und Schätzung in regulären und singulären Regressionsmodellen, Math. OF Statist.1 (1970), pp. 229–243.
B. MIDDEL and B. SCHAFFRIN: Stabilized determination of geopotential coefficients by the mixed hom BLUP approach,in: R. Rapp (ed.), Progress in the Determination of the Earth's Gravity Field, Dept. of Geodetic Sci. & Surveying, The Ohio State University, Report No.397, Columbus/Ohio 1989, pp. 27–30.
H. MORITZ: A generalized least-squares model. Studia Geophys. et Geodaet.14 (1970), pp. 353–362.
H. MORITZ: Least-squares collocation. Deutsche Geodät. Kommission A-75, Munich 1973.
B. SCHAFFRIN: Model choice and adjustment techniques in the presence of prior information. Dept. of Geodetic Sci. & Surveying, The Ohio State University, Report No.351, Columbus/Ohio 1983.
B. SCHAFFRIN: A note on linear prediction within a Gauss-Markov model linearized with respect to a random approximation;in: T. Pukkila/S. Puntanen (eds.), Proc. of the First Tampere Seminar on Linear Models (1983), Dept. of Math. Sci./Statistics, Univ. of Tampere/Finland, Report No. A-138 (1985), pp. 285–300.
B. SCHAFFRIN: Das geodätische Datum mit stochastischer Vorinformation. Deutsche Geodät. Kommission C-313, Munich 1985.
B. SCHAFFRIN: On robust collocation;in: F. Sansò (ed.), Proc. of the First Hotine-Marussi Symp. on Math. Geodesy (Rome 1985), Milano 1986, pp. 343–361.
B. SCHAFFRIN: Less sensitive tests by introducing stochastic linear hypotheses;in: T. Pukkila/S. Puntanen (eds.), Proc. of the Second Int. Tampere Conf. on Statistics, Dept. of Math. Sci./Statistics, Univ. of Tampere/Finland, Report No. A-184 (1987), pp. 647–664.
B. SCHAFFRIN: Tests for random effects based on homogeneously linear predictors. Paper presented at the Workshop on “Theory and Practice in Data Analysis”, Berlin (East), August 1988.
S.R. SEARLE: Prediction, mixed models, and variance components;in: F. Proschan/R.J. Serfling (eds.), Reliability and Biometry, SIAM: Philadelphia 1974, pp. 229–266.
R.A. SNAY: Enhancing the spatial resolution of fault slip by introducing prior information. Manus. Geodaet. (submitted March 1989).
H. THEIL and A.S. GOLDBERGER: On pure and mixed statistical estimation in economics. Int. Econ. Rev.2 (1961), pp. 65–78.
H. TOUTENBURG: Probleme linearer Vorhersagen im allgemeinen linearen Regressionsmodell. Biometr. Z.12 (1970), pp. 242–252.
H. WOLF: Über verallgemeinerte Kollokation. Z. für Vermessungswesen99 (1974), pp. 475–478.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Schaffrin, B. An alternative approach to robust collocation. Bull. Geodesique 63, 395–404 (1989). https://doi.org/10.1007/BF02519637
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF02519637